Figure 1. Overall theme for behavioral health monitoring in pig farms: (a) the pig farm is equipped with technologies to monitor individual animals and
populations with mobile devices, data computing and storage units, machine learning, decision support tools, clinical diagnosis, and treatment options; (b)
our measurement setup is shown. The ear tag with sensor board is attached to the ear lobe of individual pigs to measure vital parameters and send the
data through a smartphone app to the cloud.
Pandey, Santosh, Upender Kalwa, Taejoon Kong, Baoqing Guo, Phillip C. Gauger, David J. Peters, and Kyoung-Jin Yoon.
2021. "Behavioral Monitoring Tool for Pig Farmers: Ear Tag Sensors, Machine Intelligence, and Technology Adoption
Roadmap" Animals 11, no. 9: 2665. https://doi.org/10.3390/ani11092665
Figure 2. Prototype design and assembly: (a) CAD layout of the electronic sensor board; (b) the fabricated PCB with soldered electronic chips; (c,d) inclined view
and side view of an assembled sensor board sandwiched between the orange-colored ear tag.
Pandey, Santosh, Upender Kalwa, Taejoon Kong, Baoqing Guo, Phillip C. Gauger, David J. Peters, and Kyoung-Jin Yoon.
2021. "Behavioral Monitoring Tool for Pig Farmers: Ear Tag Sensors, Machine Intelligence, and Technology Adoption
Roadmap" Animals 11, no. 9: 2665. https://doi.org/10.3390/ani11092665
Figure 3. Animal testing: (a) two growing pigs were used for testing the electronic sensor boards;
(b) the ear tag with the sandwiched electronic sensor board was attached to the left ear of the pig. The sensors and ASIC chip were remotely controlled by
predefined awake/sleep cycles.
Figure 4. Time-series data recorded from pig testing using the electronic sensor board. Sample data from the animals is shown here as obtained from the onboard (a) temperature sensor and (b) 3-axis accelerometer. The sound sensors collected the baseline curves, but there were no useful events (e.g., coughing or
screaming) during the recorded time period.
Figure 5. Flowchart for metrics, behavioral outcomes, and indicators of poor well-being.
Figure 6. Process flow during machine intelligence involves data acquisition, preprocessing, feature set extraction, super- vised or unsupervised learning, class
definitions, performance metrics, and decision support.
https://doi.org/10.3390/ani11092665